EP0297892A2 - Apparatus and method for control of asynchronous program interrupt events in a data processing system - Google Patents

Apparatus and method for control of asynchronous program interrupt events in a data processing system Download PDF

Info

Publication number
EP0297892A2
EP0297892A2 EP88305990A EP88305990A EP0297892A2 EP 0297892 A2 EP0297892 A2 EP 0297892A2 EP 88305990 A EP88305990 A EP 88305990A EP 88305990 A EP88305990 A EP 88305990A EP 0297892 A2 EP0297892 A2 EP 0297892A2
Authority
EP
European Patent Office
Prior art keywords
mode
interrupt
signal
responding
register
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
EP88305990A
Other languages
German (de)
French (fr)
Other versions
EP0297892A3 (en
EP0297892B1 (en
Inventor
David N. Cutler
David A. Orbits
Dileep Bhandarkar
Wayne Cardoza
Richard T. Witek
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Digital Equipment Corp
Original Assignee
Digital Equipment Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Digital Equipment Corp filed Critical Digital Equipment Corp
Publication of EP0297892A2 publication Critical patent/EP0297892A2/en
Publication of EP0297892A3 publication Critical patent/EP0297892A3/en
Application granted granted Critical
Publication of EP0297892B1 publication Critical patent/EP0297892B1/en
Anticipated expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46Multiprogramming arrangements
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46Multiprogramming arrangements
    • G06F9/48Program initiating; Program switching, e.g. by interrupt
    • G06F9/4806Task transfer initiation or dispatching
    • G06F9/4812Task transfer initiation or dispatching by interrupt, e.g. masked
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/30Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/30003Arrangements for executing specific machine instructions
    • G06F9/30076Arrangements for executing specific machine instructions to perform miscellaneous control operations, e.g. NOP
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/30Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/30098Register arrangements
    • G06F9/30101Special purpose registers

Definitions

  • This invention relates generally to data processing systems and, more particularly, to events that can cause a change in the program under execution in a data processing system.
  • a control program is typically required to schedule the resources of the data processing system and provide program execution among a set of system users.
  • the control program is provided with the capability of suspending the execution of a program by saving the state or parameters of a resource (such as a data processing unit), permitting another program to utilize the resource and then restoring the resource states or parameters, and continuing execution of the suspended program.
  • resources can be multiplexed with respect to a plurality of system users and/or programs.
  • the control program is responsible for maintaining the activity of the data processing system at as high a level as possible consistent with an equitable allocation of the system resources among the potential candidates for use of the resources.
  • the currently executing program must therefore be notified that an external activity has a requirement for the resource.
  • Exemplary of external events requiring a resource in current use can be completion of an input/output (I/O) request, an interruption generated by another program (e.g., a program signal), a terminal user interrupting the program by means of a keyboard of other device for entering a signal by a system user or by the control program itself to notify the program of asynchronous events (e.g., an expired timer).
  • I/O input/output
  • AST Asynchronous System Trap
  • control program can have a need to interrupt an executing program to execute part of the control program itself in the context of the appropriate program (e.g., posting I/O completion of transfer data groups from internal buffers to program buffers, etc.).
  • interruption of a program at a given time can be inappropriate and lead to the compromise of critical data.
  • control program interruption In the related data processing systems, the capabilities required for program interruption have been implemented in the control program itself.
  • the control program implementation of program interruption require high overhead costs in the form of processing capability utilization and, in addition, require that certain events must be continually monitored. Each time a monitored event is detected, the control program must test related conditions to determine if the currently executing program is to be interrupted to execute an interruption program. Moreover, the currently executing program must be able to inform the control program that it cannot be interrupted at the present time. Finally, if the program interrupts or attempts to interrupt are frequent, then an unacceptable amount of the processing capability can used in the control program.
  • the aforementioned and other objects are accomplished, according to the present invention, by providing the data processing unit with two registers, an Asynchronous Trap Enable Register (ASTEN) and an Asynchronous Trap Summary Register (ASTSR), which control the program interrupt sequence.
  • the ASTEN register contains bits that control whether the asynchronous program interrupts are enabled for the types of execution modes, e.g., the privileged instruction or kernel mode and the nonprivileged instruction or user mode.
  • the ASTSR register contains bits that signify whether an asynchronous interrupt is pending for the associated execution modes. The pending bits in the ASTSR register are entered by the control program and the particular register bit related to the mode in which the interrupt is generated is cleared when the interrupt is executed.
  • the ASTEN and ASTSR registers are monitored along with the current processor mode and the current processor interrupt priority level to determine when an interrupt can be generated.
  • a nonprivileged instruction is provided to control the enable modes of the ASTEN register.
  • FIG. 1A the central processing unit (#1) 11 is coupled to a system bus 19.
  • Other central processing units (e.g., #N) 12 can also be coupled to the system.
  • the central processing unit(s) 11 process data according to the structure of the central processing unit(s) in conjunction with central processing unit control programs, the control programs being comprised of instructions resident in the main memory unit 15.
  • the nonresident data and instructions are typically stored in the mass storage unit(s) and are transferred to and from the main memory unit 15 via the system bus 19.
  • Input/output unit(s) ⁇ #1 ⁇ 16 couple devices such as mass memory storage units, user terminal devices and communication devices to the data processing system by means of the system bus 19.
  • the mass storage units store the data and instructions required by the data processing unit(s).
  • Sets of data and/or instructions, typically designated as pages of data and/or instructions, required for the operation of the central processing units 11 through 12, are transferred from the mass storage units, having relatively slow accessibility, to the main memory unit to which access by the central processing unit is relatively fast.
  • the bus oriented system has an advantage in the relative ease to reconfigure the system but has the disadvantage that the each system component requires control apparatus to provide an interface with the system bus. Referring next to Fig.
  • FIG. 1B a data processing system is shown in which the central processing unit(s) 11 (through 12) and the input/output unit(s) 16 (through 17) are coupled to the main memory unit 15 through a memory control unit 14, the memory control unit 14 replacing the system bus 19 and the control function performed by individual data processing system components in the bus oriented data processing configuration shown in Fig. 1A.
  • the memory control unit 14 provides a centralized control and monitoring of the transfer of data and instructions that can be more efficient than the bus oriented configuration of Fig. 1, but with the loss of flexibility.
  • the issue unit 22 is responsible for for providing (decoded) instructions to the plurality of specialized execution units comprising scalar operation address generation unit 24, at least one execution unit (#1) 25 (through execution unit ⁇ #Q ⁇ 26) and a vector operation unit 28, the vector operation unit 28 including vector operation processing unit 28A, vector operation address generation unit 28B and vector operation registers 28C.
  • the data processed by the execution units are typically extracted from the scalar registers 23 or the vector registers 28C.
  • the resulting data from the execution units are stored in the scalar registers 23, in the vector registers 28C or in the data cache memory unit 27.
  • the data cache memory unit 27 can be viewed as a cache memory unit providing an interface between the main memory unit 15 and the central processing unit 11. (The data cache memory unit 27 is shown as being coupled directly to the main memory unit in Fig. 2. As illustrated in Fig. 1A and Fig. 1B, the actual coupling can include intervening data processing apparatus.)
  • the issue unit 22 includes apparatus for determining which execution unit will process selected data and for determining when the selected execution unit is available for processing data. This latter feature includes ascertaining that the destination storage location will be available to store the processed data.
  • the instruction cache memory unit 21 stores the instructions that are decoded and forwarded to the appropriate execution unit by the issue unit.
  • the issue unit 22 has the apparatus to attempt to maximize the processing operations of the execution units.
  • the issue unit 22 includes prefetch apparatus and algorithms to ensure that the appropriate instruction (including any branch instruction) is available to the issue unit 22 as needed.
  • the plurality of execution units are, as indicated by the scalar operation address generation unit 24 and the vector operation unit 28, specialized processing devices for handling certain classes of processing operation.
  • an execution unit can be configured to handle floating point operations, or integer arithmetic operations, etc.
  • the issue unit 22 has associated therewith scalar registers 23 that can store data required for the execution of the program or for providing a record of the data processing operation.
  • one register is the Program Counter register that stores the (virtual) address of the next instruction, in the executing program instruction sequence, to be processed.
  • the scalar operation address generation unit 24 is used to convert virtual addresses to physical locations in the main memory unit 15.
  • the issue unit 22 is also responsible for reordering the data from the execution units in the correct sequence when the execution units process instructions at different rates.
  • ASTEN register 221 provides a bit position for each system operating mode that indicates if the generation of an AST interrupt signal is enabled for the respective modes. Portions of a program can be of such a nature that the interruption of the executing program may not be appropriate.
  • the instruction set includes a nonprivileged instruction, the SWASTEN instruction that permits the the currently executing program to change the enable in the mode position corresponding to the mode of the currently executing program.
  • the ASTSR register 222 also includes a bit position for each system operating mode, however a logic '1' bit stored in either bit position indicates that an AST interrupt condition is pending for the corresponding mode.
  • a storage unit 223 includes a signal indicating the mode of the presently executing program.
  • An interrupt priority level register 224 contains the current interrupt priority level of the data processing system.
  • the interrupts are processed in a preemptive priority order. In order for an interrupting source to cause an interrupt to be initiated, the priority of the interrupting source must be greater than the current processor interrupt level.
  • the previous Program Counter and Program State are stored on the kernel stack memory.
  • the new Program Counter is selected from the system control block in the operating system and is dependent on the interrupting source.
  • the new IPL is set to the IPL of the interrupting source.
  • AST interrupt's are initiated at level #1 and can therefore only interrupt programs having an IPL #0.
  • the signals stored in these register, 221, 222, 223 and 224 are monitored by monitor unit 225.
  • monitor unit 225 When signals in the ASTEN register 221, the ASTSR register 222 and the MODE register 223 have signals designating the same mode and the current processor IPL (Interrupt Priority Level) is #0, then the monitor unit generates an interrupt AST signal and an AST interrupt response sequence is initiated.
  • IPL Interrupt Priority Level
  • step 401 the monitor unit generates an AST interrupt signal in response to appropriate input signals.
  • step 402 the related bit in the ASTSR register in cleared.
  • step 403 the operating system responds to the generation of an interrupt signal. This response typically takes the form of initiation of a procedure responsive to the interrupt signal.
  • step 404 the contents of the program counter and the processor status word for the executing program are saved on the kernel stack. The saved register contents permits the data processing unit, after responding to the AST interrupt signal, to resume program execution at the point where the interrupt occurred.
  • the program for responding to the AST interrupt signal has the appropriate parameters (i.e., the context) entered in the data processing unit and instruction sequence responsive to the condition signaling an interrupt is executed.
  • the hardware privileged context block is the information saved (by a privileged instruction) when execution of the associated program is suspended. From the perspective of the present invention, the contents of the ASTEN and ASTSR registers, dependent on the associated program, must be saved to permit the return of the data processing unit to executing the associated program.
  • the hardware privileged context block includes a kernel stack pointer field 501, a user stack pointer field 502, a field 503 that includes the address number space and the ASTEN field 503A and the ASTSR field 503B.
  • the contents of the page table base register is stored in field 504.
  • step 601 the program determines that the conditions for an interrupt are to be enabled.
  • a SWASTEN (Swap ASTEN field) instruction is issued in step 602.
  • the SWASTEN instruction causes an enabling bit related to the current mode to be set in the ASTEN field.
  • the ASTSR , the ASTEN, the IPL (Interrupt Priority Level) and the current (operating) mode fields are tested to determine if the conditions are present to execute an interrupt procedure in step 603.
  • test indicates that the AST interrupt conditions are present, then the appropriate bit in the ASTSR field is cleared in step 605, and an AST interrupt response is executed in step 606.
  • the program execution continues.
  • a program can also disable delivery of AST interrupts in the future by using the SWASTEN instruction to disable AST interrupts by clearing the enabling bit in the ASTEN register.
  • an MTPR (move to processor register) instruction is issued with the ASTRR (AST request register) register as the destination of the instruction in step 652.
  • the MTPR ASTRR instruction also causes a bit corresponding to a specific operating mode to be set in the ASTSR register.
  • the ASTEN, the ASTSR, the IPL and the current mode fields are tested in step 653.
  • the bit in the corresponding mode position in the ASTSR field is cleared in step 656 and the responsive interrupt program is initiated in step 657.
  • the conditions are not present, then the currently executing program continues execution in step 655.
  • the IPL of the currently operating program must be 0 in order for the AST interrupt procedure to be executed.
  • the IPL of the currently executing program is 0, the determination is made whether the currently executing program is executing in the user mode or in the kernel mode.
  • the currently executing program is executing in the user mode, if the ASTEN and ASTSR kernel mode fields have a logic '1' bit stored therein, or if the ASTEN and ASTSR user mode fields have a logic '1' stored therein, then the appropriate mode field logic '1' bit in the ASTSR field is cleared and the appropriate (kernel mode has higher priority, then user mode) AST interrupt response is initiated.
  • the currently executing procedure is continued.
  • the ASTEN and ASTSR fields for the kernel mode is checked and, when two logic '1's bits are identified, the kernel mode AST interrupt response is initiated.
  • the two kernel mode signals are not present, then execution of the currently executing program is continued.
  • the user mode 8A typically executes application type programs that perform processing functions of immediate interest to the user.
  • the user is provided with relatively complete control in order to obtain the desired processing capabilities.
  • the instructions are typically nonprivileged in the sense that the order and selected aspects of the instruction are under control of the user.
  • the kernel mode 8B is the mode in which the operating system executes instructions.
  • the kernel mode executes all instructions available in the user mode as well as additional instructions associated with the kernel mode 8B that are privileged and therefore are not available to manipulation by a user. Privileged instructions are not allowed in user mode because they could compromise the security of other users or programs.
  • This mode of data processing system operation is reserved for instruction sequences that should execute without interruption and/or should not execute unless the data processing system is in a predetermined state.
  • Some instructions that can be executed in user mode 8A or in kernel mode 8B require a transition into the EPICODE mode 8C.
  • This mode is provided with certain privileges and certain dedicated hardware implementing the strategy to ensure noninterruptable (atomic) execution of the instruction sequence.
  • the central processing unit having pipelined execution units of Fig. 2 was implemented in the preferred embodiment subject to several constraints, however, other design implementations can utilize the present invention.
  • the central processing unit includes a plurality of execution units, each execution unit adapted to execute a class of instructions.
  • one execution unit the scalar address generating unit 24, controls the transfer of the logic signal groups between the central processing unit and the main memory unit, i.e., executes the scalar load/store instructions.
  • One execution unit is adapted to execute data shifting operations, one execution unit for floating pont add/subtract operations, one execution unit is adapted for integer and floating point multiply operations and one execution unit is adapted for integer and floating point divide operations.
  • the specialized execution units can be, but are not necessarily implemented in a pipelined configuration.
  • the other features of the central processing unit are the following.
  • the instruction in the currently executing sequence of instructions is transferred to the issue unit 22 from the instruction cache memory unit 21.
  • the issue unit the instruction is broken down into its constituent parts and data-dependent control signals and address signals are generated therefrom.
  • All source and destination registers for the instruction must be available, i.e., no write operations to be needed register can be outstanding.
  • the register write path must be available at the future cycle in which this instruction will store the processed quantity.
  • the execution unit to be required for processing the instruction during the execution must be available to perform the operation.
  • a vector operation reserves an execution unit for the duration of the vector operation.
  • the load/store unit busy flag When a memory load/store instruction experiences a cache memory unit miss, the load/store unit busy flag will cause the subsequent load/store instructions to be delayed until the cache memory miss response is complete.
  • the destination register and the write path cycle for the result are reserved.
  • operand set-up all instruction-independent register addresses are generated, operands are read and stored, and data-dependent control signals are generated.
  • the instruction operands and control signals are passed to the the associated execution unit for execution.
  • the result generated by the execution unit is stored in the register files or in the data cache memory unit 15 as appropriate. Once an instruction issues, the result of the processing may not be available for several machine cycles. Meanwhile, in the next machine cycle, the next instruction can be decoded and can be issued when the requisite issue conditions are satisfied.
  • the instructions are decoded and issued in the normal instruction sequence, but the results can be stored in a different order because of the of the varying instruction execution times of the execution units.
  • This out of order storing complicates the exception handling and the retry of failing instructions.
  • these events are relatively rare the out of order storing provides execution and hardware advantages.
  • the AST (Asynchronous System Trap) events of the preferred embodiment are on a per program basis. These events are initiated by software programs. Each program (or process) has a set of values that are entered in the ASTEN and ASTSR fields while the program is in execution. The contents of these fields determine when the currently executing program is interrupted to execute a privileged control program procedure in the context environment of the program or a nonprivileged program procedure in the context environment of the program.
  • the state of the ASTEN field is controlled by the program and the enable state for executing program in the current mode can be changed by the SWASTEN instruction.
  • the state of the ASTSR field is controlled by a control program.
  • the control program When an event occurs that requires interruption of the currently executing program, the control program writes the mode in which the corresponding interrupt procedure will execute to the ASTRR register. Writing to the ASTRR register causes a bit to be entered in the ASTSR field corresponding to the mode associated with the ASTRR register.
  • the ASTEN and ASTSR fields are part of a program's context environment. These fields are saved and restored when context switching between programs is performed.
  • the processing unit constantly monitors the state of the ASTEN and ASTSR registers, the current operating mode of the processor, and the current processor interrupt priority level. When the current processor interrupt priority level is zero and the bits corresponding to the current or more privileged processor mode in the ASTSR register and in the ASTEN register are set, then an AST interrupt response is initiated. These conditions are tested in response to certain instructions.
  • the hardware responds to this interrupt by saving the contents of the program counter and the processor status word and then suspends the currently executing program. The saving of the register contents permits the data processing unit to continue execution of the suspended program when the AST interrupt procedure is completed.
  • SWASTEN nonprivileged or user mode instruction
  • the current invention provides a mechanism for control of the interrupt process on a per program basis.
  • the current mechanism is not tied to a software interrupt procedure and never generates an interrupt in the absence of a detected interrupt condition.
  • the interrupt execution can occur without the necessity for the control program to poll related event conditions or to have the executing program notify the control program when interruption is not acceptable.
  • the SWASTEN and the MTPR instructions are executed in the EPICODE mode.
  • multistep instructions can be executed as a unit (typically interrupts are disabled) and can even be stored in a dedicated portion of memory to eliminate the paging operation. In this manner, the test of the various fields can be performed efficiently. It will be clear that an interrupt response will be generated in response to a change in the processing environment, i.e., either a change in the interrupt enable conditions for the current operating mode or identification of an interrupt event.
  • the ASTEN and ASTSR registers have been described as physical registers. However, it will be clear that these registers can be implemented as fields in a data block.

Abstract

In a data processing system having a kernel mode (i.e., for executing privileged instructions) and a user mode of operation, apparatus for responding to interrupt conditions includes a first register (221), subject to the control of the currently executing program for enabling the generation of a mode-related interrupt signal and includes a second register (222) for indicating the presence of a pending mode-related interrupt condition and a third register (223) for requesting a mode-related interrupt be entered in the second register. The mode of operation and the enable and pending interrupt condition registers are monitored (225) and when the signals in the two registers have the appropriate relationship, an interrupt signal is generated to which a control program will respond. The contents of the first register can be controlled by the currently executing program which can control the enabling signal for the currently executing mode. The pending interrupt condition and the request registers may be accessed only from the privileged mode of operation.

Description

    BACKGROUND OF THE INVENTION 1. Field of the Invention
  • This invention relates generally to data processing systems and, more particularly, to events that can cause a change in the program under execution in a data processing system.
  • 2. Description of the Related Art
  • In modern high performance data processing systems, the processing capability is sufficient to permit a multiplicity of activities to be carried on concurrently. Without the concurrency of activities, the resources of the data processing system would be under-utilized. A control program is typically required to schedule the resources of the data processing system and provide program execution among a set of system users. The control program is provided with the capability of suspending the execution of a program by saving the state or parameters of a resource (such as a data processing unit), permitting another program to utilize the resource and then restoring the resource states or parameters, and continuing execution of the suspended program. In this manner, resources can be multiplexed with respect to a plurality of system users and/or programs. The control program is responsible for maintaining the activity of the data processing system at as high a level as possible consistent with an equitable allocation of the system resources among the potential candidates for use of the resources.
  • While an activity is being executed in response to the current program, the interruption of the executing activity can be necessary to respond to events that occur outside the cognizance of the control program. The currently executing program must therefore be notified that an external activity has a requirement for the resource. Exemplary of external events requiring a resource in current use can be completion of an input/output (I/O) request, an interruption generated by another program (e.g., a program signal), a terminal user interrupting the program by means of a keyboard of other device for entering a signal by a system user or by the control program itself to notify the program of asynchronous events (e.g., an expired timer). These events are typically referred to as AST (Asynchronous System Trap) events. Indeed, the control program can have a need to interrupt an executing program to execute part of the control program itself in the context of the appropriate program (e.g., posting I/O completion of transfer data groups from internal buffers to program buffers, etc.). However, the interruption of a program at a given time can be inappropriate and lead to the compromise of critical data.
  • In the related data processing systems, the capabilities required for program interruption have been implemented in the control program itself. The control program implementation of program interruption require high overhead costs in the form of processing capability utilization and, in addition, require that certain events must be continually monitored. Each time a monitored event is detected, the control program must test related conditions to determine if the currently executing program is to be interrupted to execute an interruption program. Moreover, the currently executing program must be able to inform the control program that it cannot be interrupted at the present time. Finally, if the program interrupts or attempts to interrupt are frequent, then an unacceptable amount of the processing capability can used in the control program.
  • A need has therefore been felt for apparatus and method to control program interrupts that is directly available to nonprivileged programs and which do not contain the inefficiencies involved in a software program implementation.
  • FEATURES OF THE INVENTION
  • It is an object of the present invention to provide an improved data processing unit.
  • It is a feature of the present invention to provide a data processing system having improved control of the interruption of the currently executing program.
  • It is another feature of the present invention to provide a mechanism for indicating when an interrupt condition is enabled in a particular mode and when an interrupt condition is present in a particular mode.
  • It is still another feature of the present invention to monitor the interrupt enabled mechanism and the interrupt present mechanism and when the conditions coincide, to generate an interrupt signal.
  • It is yet another feature of the present invention to provide a nonprivileged instruction to control the enabling and disabling of program interruption by the current processor mode program.
  • SUMMARY OF THE INVENTION
  • The aforementioned and other objects are accomplished, according to the present invention, by providing the data processing unit with two registers, an Asynchronous Trap Enable Register (ASTEN) and an Asynchronous Trap Summary Register (ASTSR), which control the program interrupt sequence. The ASTEN register contains bits that control whether the asynchronous program interrupts are enabled for the types of execution modes, e.g., the privileged instruction or kernel mode and the nonprivileged instruction or user mode. The ASTSR register contains bits that signify whether an asynchronous interrupt is pending for the associated execution modes. The pending bits in the ASTSR register are entered by the control program and the particular register bit related to the mode in which the interrupt is generated is cleared when the interrupt is executed. The ASTEN and ASTSR registers are monitored along with the current processor mode and the current processor interrupt priority level to determine when an interrupt can be generated. A nonprivileged instruction is provided to control the enable modes of the ASTEN register.
  • These and other features of the present invention will be understood upon reading of the following description along with the drawings.
  • BRIEF DESCRIPTION OF THE DRAWINGS
    • Figure 1A and Figure 1B are examples of data processing system implementations capable of using the present invention.
    • Figure 2 is an example of a central processing unit of a data processing unit capable of using the present invention.
    • Figure 3 is block diagram of the apparatus implementing the present invention.
    • Figure 4 is flow diagram illustrating the processing unit response to an interrupt signal generated by the present invention.
    • Figure 5 is the hardware privileged context block according to the preferred embodiment of the present invention.
    • Figure 6A is flow diagram illustrating how an interrupt is generated in response to activity of the program; while Figure 6B illustrates how an interrupt is generated in response to activity identifying an interrupt condition according to the present invention.
    • Figure 7 indicates the instructions resulting in examination of the ASTEN and ASTSR registers and illustrates the test procedure.
    • Figure 8 is a diagrammatic illustration of the relationship of the data processing system operating system modes.
    DESCRIPTION OF THE PREFERRED EMBODIMENT 1. Detailed Description of the Figures
  • Referring now to Fig. 1A and Fig. 1B, two exemplary data processing system configurations capable of using the present invention are shown. In Fig. 1A, the central processing unit (#1) 11 is coupled to a system bus 19. Other central processing units (e.g., #N) 12 can also be coupled to the system. The central processing unit(s) 11 (through 12) process data according to the structure of the central processing unit(s) in conjunction with central processing unit control programs, the control programs being comprised of instructions resident in the main memory unit 15. The nonresident data and instructions are typically stored in the mass storage unit(s) and are transferred to and from the main memory unit 15 via the system bus 19. Input/output unit(s) {#1} 16 (through {#M} 17) couple devices such as mass memory storage units, user terminal devices and communication devices to the data processing system by means of the system bus 19. The mass storage units store the data and instructions required by the data processing unit(s). Sets of data and/or instructions, typically designated as pages of data and/or instructions, required for the operation of the central processing units 11 through 12, are transferred from the mass storage units, having relatively slow accessibility, to the main memory unit to which access by the central processing unit is relatively fast. The bus oriented system has an advantage in the relative ease to reconfigure the system but has the disadvantage that the each system component requires control apparatus to provide an interface with the system bus. Referring next to Fig. 1B, a data processing system is shown in which the central processing unit(s) 11 (through 12) and the input/output unit(s) 16 (through 17) are coupled to the main memory unit 15 through a memory control unit 14, the memory control unit 14 replacing the system bus 19 and the control function performed by individual data processing system components in the bus oriented data processing configuration shown in Fig. 1A. The memory control unit 14 provides a centralized control and monitoring of the transfer of data and instructions that can be more efficient than the bus oriented configuration of Fig. 1, but with the loss of flexibility.
  • Referring next to Fig. 2, a block diagram of an exemplary central processing unit capable of effective utilization of the present invention is illustrated. The issue unit 22 is responsible for for providing (decoded) instructions to the plurality of specialized execution units comprising scalar operation address generation unit 24, at least one execution unit (#1) 25 (through execution unit {#Q} 26) and a vector operation unit 28, the vector operation unit 28 including vector operation processing unit 28A, vector operation address generation unit 28B and vector operation registers 28C. The data processed by the execution units are typically extracted from the scalar registers 23 or the vector registers 28C. The resulting data from the execution units are stored in the scalar registers 23, in the vector registers 28C or in the data cache memory unit 27. The data cache memory unit 27 can be viewed as a cache memory unit providing an interface between the main memory unit 15 and the central processing unit 11. (The data cache memory unit 27 is shown as being coupled directly to the main memory unit in Fig. 2. As illustrated in Fig. 1A and Fig. 1B, the actual coupling can include intervening data processing apparatus.) The issue unit 22 includes apparatus for determining which execution unit will process selected data and for determining when the selected execution unit is available for processing data. This latter feature includes ascertaining that the destination storage location will be available to store the processed data. The instruction cache memory unit 21 stores the instructions that are decoded and forwarded to the appropriate execution unit by the issue unit. The issue unit 22 has the apparatus to attempt to maximize the processing operations of the execution units. Thus, the issue unit 22 includes prefetch apparatus and algorithms to ensure that the appropriate instruction (including any branch instruction) is available to the issue unit 22 as needed. The plurality of execution units are, as indicated by the scalar operation address generation unit 24 and the vector operation unit 28, specialized processing devices for handling certain classes of processing operation. For example, an execution unit can be configured to handle floating point operations, or integer arithmetic operations, etc. The issue unit 22 has associated therewith scalar registers 23 that can store data required for the execution of the program or for providing a record of the data processing operation. For example, one register is the Program Counter register that stores the (virtual) address of the next instruction, in the executing program instruction sequence, to be processed. The scalar operation address generation unit 24 is used to convert virtual addresses to physical locations in the main memory unit 15. The issue unit 22 is also responsible for reordering the data from the execution units in the correct sequence when the execution units process instructions at different rates.
  • Referring to Fig. 3, the apparatus controlling the generation of an AST interrupt signal is illustrated. As ASTEN register 221 provides a bit position for each system operating mode that indicates if the generation of an AST interrupt signal is enabled for the respective modes. Portions of a program can be of such a nature that the interruption of the executing program may not be appropriate. In order to extend the usefulness of the ASTEN register 221, the instruction set includes a nonprivileged instruction, the SWASTEN instruction that permits the the currently executing program to change the enable in the mode position corresponding to the mode of the currently executing program. The ASTSR register 222 also includes a bit position for each system operating mode, however a logic '1' bit stored in either bit position indicates that an AST interrupt condition is pending for the corresponding mode. A storage unit 223 includes a signal indicating the mode of the presently executing program. An interrupt priority level register 224 contains the current interrupt priority level of the data processing system. In the preferred embodiment, the interrupts are processed in a preemptive priority order. In order for an interrupting source to cause an interrupt to be initiated, the priority of the interrupting source must be greater than the current processor interrupt level. When an interrupt is initiated, the previous Program Counter and Program State are stored on the kernel stack memory. The new Program Counter is selected from the system control block in the operating system and is dependent on the interrupting source. The new IPL is set to the IPL of the interrupting source. Thus, interrupts for higher source IPL's can interrupt lower central processing unit IPL's, but not equal or higher IPL's. AST interrupt's are initiated at level #1 and can therefore only interrupt programs having an IPL #0. The signals stored in these register, 221, 222, 223 and 224 are monitored by monitor unit 225. When signals in the ASTEN register 221, the ASTSR register 222 and the MODE register 223 have signals designating the same mode and the current processor IPL (Interrupt Priority Level) is #0, then the monitor unit generates an interrupt AST signal and an AST interrupt response sequence is initiated.
  • Referring to Fig. 4, the response of the data processing unit to an AST interrupt signal generated by the monitor unit 225 if Fig. 3 is illustrated. In step 401, the monitor unit generates an AST interrupt signal in response to appropriate input signals. In step 402, the related bit in the ASTSR register in cleared. In step 403, the operating system responds to the generation of an interrupt signal. This response typically takes the form of initiation of a procedure responsive to the interrupt signal. In step 404, the contents of the program counter and the processor status word for the executing program are saved on the kernel stack. The saved register contents permits the data processing unit, after responding to the AST interrupt signal, to resume program execution at the point where the interrupt occurred. The program for responding to the AST interrupt signal has the appropriate parameters (i.e., the context) entered in the data processing unit and instruction sequence responsive to the condition signaling an interrupt is executed.
  • Referring next to Fig. 5, the format of the hardware privileged context block is shown. The hardware privileged context block is the information saved (by a privileged instruction) when execution of the associated program is suspended. From the perspective of the present invention, the contents of the ASTEN and ASTSR registers, dependent on the associated program, must be saved to permit the return of the data processing unit to executing the associated program. The hardware privileged context block includes a kernel stack pointer field 501, a user stack pointer field 502, a field 503 that includes the address number space and the ASTEN field 503A and the ASTSR field 503B. The contents of the page table base register is stored in field 504.
  • Referring to Figure 6A, the method by which a program enables the delivery of pending AST interrupts is illustrated. In step 601, the program determines that the conditions for an interrupt are to be enabled. To implement that change, a SWASTEN (Swap ASTEN field) instruction is issued in step 602. The SWASTEN instruction causes an enabling bit related to the current mode to be set in the ASTEN field. As a result of that instruction, the ASTSR , the ASTEN, the IPL (Interrupt Priority Level) and the current (operating) mode fields are tested to determine if the conditions are present to execute an interrupt procedure in step 603. When the test indicates that the AST interrupt conditions are present, then the appropriate bit in the ASTSR field is cleared in step 605, and an AST interrupt response is executed in step 606. When the test indicates that the conditions are not present, then the program execution continues. A program can also disable delivery of AST interrupts in the future by using the SWASTEN instruction to disable AST interrupts by clearing the enabling bit in the ASTEN register.
  • Referring to Fig. 6B, the generation of an AST interrupt event according to the present invention is shown. As a result of the identification of an interrupt condition in step 651, an MTPR (move to processor register) instruction is issued with the ASTRR (AST request register) register as the destination of the instruction in step 652. The MTPR ASTRR instruction also causes a bit corresponding to a specific operating mode to be set in the ASTSR register. In response to the MTPR ASTRR instruction, the ASTEN, the ASTSR, the IPL and the current mode fields are tested in step 653. When the AST interrupt conditions for the data processing unit are present in step 653, then the bit in the corresponding mode position in the ASTSR field is cleared in step 656 and the responsive interrupt program is initiated in step 657. When the conditions are not present, then the currently executing program continues execution in step 655.
  • Referring next to Fig. 7, instructions using the test in steps 603 and 604 in Fig. 6A and in steps 653 and 654 in Fig. 6B as well as details of the test are shown according to the preferred embodiment. The test involving the ASTEN and ASTSR fields are executed for the SWIPL (Swap Interrupt Priority Level) instruction 701, the SWASTEN (Swap ASTEN) instruction 702, the REI (Return from Exception or Interrupt) instruction 703 and the MTPR (Move To Processor Register) ASTRR instruction. It will be clear that each of these instructions can result in the enabling of an AST interrupt procedure and therefore this condition must be tested. The test logic structure is illustrated in 705. The determination of the IPL value for the currently executing program is examined. Because the IPL value of the AST interrupt programs is 1, then the IPL of the currently operating program must be 0 in order for the AST interrupt procedure to be executed. When the IPL of the currently executing program is 0, the the determination is made whether the currently executing program is executing in the user mode or in the kernel mode. When the currently executing program is executing in the user mode, if the ASTEN and ASTSR kernel mode fields have a logic '1' bit stored therein, or if the ASTEN and ASTSR user mode fields have a logic '1' stored therein, then the appropriate mode field logic '1' bit in the ASTSR field is cleared and the appropriate (kernel mode has higher priority, then user mode) AST interrupt response is initiated. When the ASTEN and ASTSR fields do not have the appropriate values, then the currently executing procedure is continued. When the currently executing program is executing in the kernel mode, then the ASTEN and ASTSR fields for the kernel mode is checked and, when two logic '1's bits are identified, the kernel mode AST interrupt response is initiated. When the two kernel mode signals are not present, then execution of the currently executing program is continued.
  • Referring next to Fig. 8, the relationship of the two typical operating system modes and the EPICODE mode is shown. The user mode 8A typically executes application type programs that perform processing functions of immediate interest to the user. The user is provided with relatively complete control in order to obtain the desired processing capabilities. The instructions are typically nonprivileged in the sense that the order and selected aspects of the instruction are under control of the user. The kernel mode 8B is the mode in which the operating system executes instructions. The kernel mode executes all instructions available in the user mode as well as additional instructions associated with the kernel mode 8B that are privileged and therefore are not available to manipulation by a user. Privileged instructions are not allowed in user mode because they could compromise the security of other users or programs. This mode of data processing system operation is reserved for instruction sequences that should execute without interruption and/or should not execute unless the data processing system is in a predetermined state. Some instructions that can be executed in user mode 8A or in kernel mode 8B require a transition into the EPICODE mode 8C. This mode is provided with certain privileges and certain dedicated hardware implementing the strategy to ensure noninterruptable (atomic) execution of the instruction sequence.
  • 2. Operation of the Preferred Embodiment
  • The central processing unit having pipelined execution units of Fig. 2 was implemented in the preferred embodiment subject to several constraints, however, other design implementations can utilize the present invention. The central processing unit includes a plurality of execution units, each execution unit adapted to execute a class of instructions. By way of example, one execution unit, the scalar address generating unit 24, controls the transfer of the logic signal groups between the central processing unit and the main memory unit, i.e., executes the scalar load/store instructions. One execution unit is adapted to execute data shifting operations, one execution unit for floating pont add/subtract operations, one execution unit is adapted for integer and floating point multiply operations and one execution unit is adapted for integer and floating point divide operations. The specialized execution units can be, but are not necessarily implemented in a pipelined configuration. The other features of the central processing unit are the following. The instruction in the currently executing sequence of instructions is transferred to the issue unit 22 from the instruction cache memory unit 21. In the issue unit, the instruction is broken down into its constituent parts and data-dependent control signals and address signals are generated therefrom. However, before an instruction can begin execution (i.e., be issued), several constraints must be satisfied. All source and destination registers for the instruction must be available, i.e., no write operations to be needed register can be outstanding. The register write path must be available at the future cycle in which this instruction will store the processed quantity. The execution unit to be required for processing the instruction during the execution must be available to perform the operation. With respect to the vector operation unit, a vector operation reserves an execution unit for the duration of the vector operation. When a memory load/store instruction experiences a cache memory unit miss, the load/store unit busy flag will cause the subsequent load/store instructions to be delayed until the cache memory miss response is complete. When an instruction does issue, the destination register and the write path cycle for the result are reserved. During operand set-up, all instruction-independent register addresses are generated, operands are read and stored, and data-dependent control signals are generated. The instruction operands and control signals are passed to the the associated execution unit for execution. The result generated by the execution unit is stored in the register files or in the data cache memory unit 15 as appropriate. Once an instruction issues, the result of the processing may not be available for several machine cycles. Meanwhile, in the next machine cycle, the next instruction can be decoded and can be issued when the requisite issue conditions are satisfied. Thus, the instructions are decoded and issued in the normal instruction sequence, but the results can be stored in a different order because of the of the varying instruction execution times of the execution units. This out of order storing complicates the exception handling and the retry of failing instructions. However, these events are relatively rare the out of order storing provides execution and hardware advantages.
  • The AST (Asynchronous System Trap) events of the preferred embodiment are on a per program basis. These events are initiated by software programs. Each program (or process) has a set of values that are entered in the ASTEN and ASTSR fields while the program is in execution. The contents of these fields determine when the currently executing program is interrupted to execute a privileged control program procedure in the context environment of the program or a nonprivileged program procedure in the context environment of the program. The state of the ASTEN field is controlled by the program and the enable state for executing program in the current mode can be changed by the SWASTEN instruction. The state of the ASTSR field is controlled by a control program. When an event occurs that requires interruption of the currently executing program, the control program writes the mode in which the corresponding interrupt procedure will execute to the ASTRR register. Writing to the ASTRR register causes a bit to be entered in the ASTSR field corresponding to the mode associated with the ASTRR register. The ASTEN and ASTSR fields are part of a program's context environment. These fields are saved and restored when context switching between programs is performed.
  • The processing unit constantly monitors the state of the ASTEN and ASTSR registers, the current operating mode of the processor, and the current processor interrupt priority level. When the current processor interrupt priority level is zero and the bits corresponding to the current or more privileged processor mode in the ASTSR register and in the ASTEN register are set, then an AST interrupt response is initiated. These conditions are tested in response to certain instructions. The hardware responds to this interrupt by saving the contents of the program counter and the processor status word and then suspends the currently executing program. The saving of the register contents permits the data processing unit to continue execution of the suspended program when the AST interrupt procedure is completed.
  • The nonprivileged or user mode instruction (SWASTEN) is provided so that the state of the enable mode from which the instruction is executed can be changed in the ASTEN register. In this manner, the owner of a process can determine its interruptability.
  • The current invention provides a mechanism for control of the interrupt process on a per program basis. The current mechanism is not tied to a software interrupt procedure and never generates an interrupt in the absence of a detected interrupt condition. The interrupt execution can occur without the necessity for the control program to poll related event conditions or to have the executing program notify the control program when interruption is not acceptable.
  • In the preferred embodiment, the SWASTEN and the MTPR instructions are executed in the EPICODE mode. In this processing environment, multistep instructions can be executed as a unit (typically interrupts are disabled) and can even be stored in a dedicated portion of memory to eliminate the paging operation. In this manner, the test of the various fields can be performed efficiently. It will be clear that an interrupt response will be generated in response to a change in the processing environment, i.e., either a change in the interrupt enable conditions for the current operating mode or identification of an interrupt event. The ASTEN and ASTSR registers have been described as physical registers. However, it will be clear that these registers can be implemented as fields in a data block.
  • The foregoing description is included to illustrate the operation of the preferred embodiment and is not meant to limit the scope of the invention. The scope of the invention is to be limited only by the following claims. From the foregoing description, many variations will be apparent to those skilled in the art that would yet be encompassed by the spirit and scope of the invention.

Claims (23)

1. Apparatus for responding to an interrupt condition in a data processing system having a kernel mode of operation for executing privileged and nonprivileged instructions and a user mode of operation for executing nonprivileged instructions, comprising:
      first register means having a first position related to said user mode of operation and a second position related to said kernel mode of operation, a signal in either of said positions enabling generation of an interrupt signal for said related mode of operation;
      second register means having a position related to said user mode of operation and position related to said kernel mode of operation, a signal in either position indicating a presence of an interrupt condition in said related mode of operation;
      third register means storing a signal designating a mode of operation;
      fourth register means for storing the interrupt priority level of the current program; and
      monitor means for generating an interrupt signal when said first, second and third register means have signals stored therein related to a same mode of operation and said fourth register means has a one of a set of predefined values.
2. The apparatus for responding to an interrupt condition of Claim 1 wherein a currently executing program can control a signal in a mode position in said first register means identical to a mode of operation of said currently executing program.
3. The apparatus for responding to an interrupt condition of Claim 1 further comprising a fourth register means for storing an indication of an interrupt priority level, said monitor means receiving signals from said fourth register means, said interrupt signal being generated when said indication has a preselected value in addition to said first, second and third register means conditions.
4. The apparatus for responding to an interrupt condition of Claim 1 wherein said interrupt signal causes a response to said interrupt condition related to a same or a more privileged mode of operation as a mode of operation of said currently executing program.
5. The apparatus for responding to an interrupt condition of Claim 4 wherein said interrupt signal causes a signal related to said mode of operation of said currently executing program to be removed from said second register means.
6. The apparatus for responding to an interrupt condition of Claim 2 wherein control of user mode signals stored in said first register means is provided by a nonprivileged instruction.
7. The apparatus for responding to an interrupt condition of Claim 1 wherein said contents of said first and said second register means are a portion of a stored program context.
8. The apparatus for responding to an interrupt condition of Claim 1 wherein instructions changing signals in said first and said second register means activate said monitor means.
9. The apparatus for responding to an interrupt condition of Claim 1 wherein selected instructions cause said monitor means to generate said interrupt signal when said second position of said first and and said second register means have a preselected signal stored therein when said data processing system is in said kernel mode of operation.
10. The apparatus for responding to an interrupt condition of Claim 9 wherein said selected instructions cause said monitor means to generate said interrupt signal when said preselected signal is stored in said second position of said first and said second register means when said data processing system is in said user mode of operation, said selected instructions causing said monitor means to generate said interrupt signal when said preselected signal is stored in said first position of said first and said second register means and not simultaneously stored in said second position of said first and said second register means during said user mode of operation.
11. The apparatus for responding to an interrupt condition of Claim 1 wherein selected instructions enable said monitor means.
12. The apparatus for responding to an interrupt condition of Claim 11 wherein said selected instructions include an instruction for changing interrupt priority level information, an instruction for changing signals stored in said first register, an instruction for changing signals stored in said second register and an instruction for returning to data processing system operation after execution of an exception or interrupt subroutine.
13. The apparatus for responding to an interrupt condition of Claim 12 wherein said signal stored in said second register position related to said interrupt signal is removed.
14. The apparatus for responding to an interrupt condition of Claim 13 wherein said data processing system includes a third mode of operation, said selected instructions being executed in said third mode of operation.
15. The apparatus for responding to an interrupt condition of Claim 1 wherein a user program can control signals stored in said first position of said first register means.
16. The apparatus for responding to an interrupt condition of Claim 3 wherein said preselected indication value corresponds to the lowest priority interrupt level.
17. The apparatus for responding to an interrupt condition of Claim 1 wherein a position in said first register means corresponding to said interrupt signal has a signal stored therein altered.
18. A method of responding to asynchronous interrupt conditions comprising the steps of:
      storing in first register means a mode-related enabling signal indicating that a an interrupt condition in the related mode can be responded to;
      storing in a second register means a mode-related interrupt condition present signal indicating a presence of an interrupt condition in the related mode; and
      issuing an interrupt signal when corresponding signals are present for a mode in which a processor is currently executing.
19. The method for responding to asynchronous interrupt conditions of Claim 16 wherein said storing in first register step includes the step of storing a one of said mode-related enable signals in response to an instruction executing in a same data processing system mode as said one mode-related enable signal.
20. The method for responding to asynchronous interrupt conditions of Claim 18 wherein said issuing step includes the step of executing a one of a plurality of selected instructions.
21. The method for responding to asynchronous interrupt conditions of Claim 18, said data processing system including a user mode for executing nonprivileged instructions and a kernel mode for executing privileged and nonprivileged instructions, wherein said issuing step includes the step of issuing an interrupt signal when said corresponding signals are present for both said user mode of operation and said kernel mode of operation when said data processing is operating in said user mode of operation, said interrupt signal responding to said kernel mode corresponding signals.
22. Apparatus for responding to an interrupt condition in a data processing system having a first and a second mode of operation comprising:
      first register means for storing signals enabling an interrupt signal for said first and said second mode of operation;
      second register means for storing signals related to an interrupt condition for said first and said second mode of operation; and
      interrupt means for responding to said interrupt condition when a current mode of operation, an enabling signal and an interrupt condition signal are related to a same mode of operation.
23. Apparatus for responding to an interrupt condition of Claim 22 wherein said data processing system includes selected instructions having subroutines determining when said current mode of operation, said enabling signal and said interrupt condition signal all relate to said same mode of operation.
EP88305990A 1987-07-01 1988-06-30 Apparatus and method for control of asynchronous program interrupt events in a data processing system Expired - Lifetime EP0297892B1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US6943687A 1987-07-01 1987-07-01
US69436 1987-07-01

Publications (3)

Publication Number Publication Date
EP0297892A2 true EP0297892A2 (en) 1989-01-04
EP0297892A3 EP0297892A3 (en) 1992-02-12
EP0297892B1 EP0297892B1 (en) 1994-11-30

Family

ID=22088968

Family Applications (1)

Application Number Title Priority Date Filing Date
EP88305990A Expired - Lifetime EP0297892B1 (en) 1987-07-01 1988-06-30 Apparatus and method for control of asynchronous program interrupt events in a data processing system

Country Status (9)

Country Link
EP (1) EP0297892B1 (en)
JP (1) JPH0668725B2 (en)
KR (1) KR970004512B1 (en)
CN (1) CN1014842B (en)
AU (1) AU626067B2 (en)
BR (1) BR8803377A (en)
CA (1) CA1302582C (en)
DE (1) DE3852220T2 (en)
IN (1) IN171220B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0442714A2 (en) * 1990-02-13 1991-08-21 International Business Machines Corporation Interrupt handling in a data processing system
EP1889165A2 (en) * 2005-05-16 2008-02-20 Microsoft Corporation Method for delivering interrupts to user mode drivers
US20080065804A1 (en) * 2006-09-08 2008-03-13 Gautham Chinya Event handling for architectural events at high privilege levels
EP2137617B1 (en) * 2007-03-14 2018-12-05 Xmos Ltd Processor instruction set

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN100367213C (en) * 2004-09-30 2008-02-06 黄英哲 System and method with automatically backing up and recovering data in register
CN100365605C (en) * 2005-12-02 2008-01-30 北京中星微电子有限公司 Apparatus and method of multi-grade interrupt applicant

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3560935A (en) * 1968-03-15 1971-02-02 Burroughs Corp Interrupt apparatus for a modular data processing system

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0693225B2 (en) * 1985-09-20 1994-11-16 日本電気株式会社 Event processing method

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3560935A (en) * 1968-03-15 1971-02-02 Burroughs Corp Interrupt apparatus for a modular data processing system

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
COMPUTER DESIGN. vol. 18, no. 12, December 1979, LITTLETON, MASSACHUSETTS US pages 14 - 19; R.J. GALLAGHER: 'Hardware interrupt structure for a distributed processing system' *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0442714A2 (en) * 1990-02-13 1991-08-21 International Business Machines Corporation Interrupt handling in a data processing system
EP0442714A3 (en) * 1990-02-13 1994-05-18 Ibm Interrupt handling in a data processing system
EP1889165A2 (en) * 2005-05-16 2008-02-20 Microsoft Corporation Method for delivering interrupts to user mode drivers
EP1889165A4 (en) * 2005-05-16 2009-09-16 Microsoft Corp Method for delivering interrupts to user mode drivers
US20080065804A1 (en) * 2006-09-08 2008-03-13 Gautham Chinya Event handling for architectural events at high privilege levels
US8214574B2 (en) * 2006-09-08 2012-07-03 Intel Corporation Event handling for architectural events at high privilege levels
EP2137617B1 (en) * 2007-03-14 2018-12-05 Xmos Ltd Processor instruction set

Also Published As

Publication number Publication date
KR970004512B1 (en) 1997-03-28
CA1302582C (en) 1992-06-02
DE3852220D1 (en) 1995-01-12
AU1863788A (en) 1989-01-05
EP0297892A3 (en) 1992-02-12
KR890002764A (en) 1989-04-11
JPS6488639A (en) 1989-04-03
JPH0668725B2 (en) 1994-08-31
BR8803377A (en) 1989-01-24
IN171220B (en) 1992-08-15
DE3852220T2 (en) 1995-06-08
EP0297892B1 (en) 1994-11-30
CN1030311A (en) 1989-01-11
CN1014842B (en) 1991-11-20
AU626067B2 (en) 1992-07-23

Similar Documents

Publication Publication Date Title
US5148544A (en) Apparatus and method for control of asynchronous program interrupt events in a data processing system
US5218712A (en) Providing a data processor with a user-mode accessible mode of operations in which the processor performs processing operations without interruption
EP0333366B1 (en) Context switching method and apparatus for use in a vector processing system
US5317717A (en) Apparatus and method for main memory unit protection using access and fault logic signals
US5043867A (en) Exception reporting mechanism for a vector processor
US5613114A (en) System and method for custom context switching
US5113521A (en) Method and apparatus for handling faults of vector instructions causing memory management exceptions
US4074353A (en) Trap mechanism for a data processing system
US5361375A (en) Virtual computer system having input/output interrupt control of virtual machines
US5377337A (en) Method and means for enabling virtual addressing control by software users over a hardware page transfer control entity
US5341482A (en) Method for synchronization of arithmetic exceptions in central processing units having pipelined execution units simultaneously executing instructions
EP0297893A2 (en) Apparatus and method for recovering from page faults in vector data processing operations
EP0335515A2 (en) Method and apparatus for executing instructions for a vector processing system
US4725946A (en) P and V instructions for semaphore architecture in a multiprogramming/multiprocessing environment
US5291581A (en) Apparatus and method for synchronization of access to main memory signal groups in a multiprocessor data processing system
EP0123337A2 (en) A method and apparatus for coordinating execution of an instruction by a coprocessor
EP0297892B1 (en) Apparatus and method for control of asynchronous program interrupt events in a data processing system
EP0297891B1 (en) Apparatus and method for main memory unit protection using access and fault logic signals
EP0301707B1 (en) Apparatus and method for providing an extended processing environment on nonmicrocoded data processing system
US5278840A (en) Apparatus and method for data induced condition signalling
EP0206335B1 (en) Interruption method for a data processing system
EP0307448B1 (en) Apparatus and method for synchronization of arithmetic exceptions in parallel pipelined execution units
CA1302580C (en) Apparatus and method for using lockout for synchronization of access to main memory signal groups in a multiprocessor data processing system
EP0297890B1 (en) Apparatus and method for data induced condition signaling
EP0333365A2 (en) Method and apparatus for handling asynchronous memory management exceptions by a vector processor

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

AK Designated contracting states

Kind code of ref document: A2

Designated state(s): CH DE FR GB IT LI NL SE

PUAL Search report despatched

Free format text: ORIGINAL CODE: 0009013

AK Designated contracting states

Kind code of ref document: A3

Designated state(s): CH DE FR GB IT LI NL SE

17P Request for examination filed

Effective date: 19920619

17Q First examination report despatched

Effective date: 19930630

GRAA (expected) grant

Free format text: ORIGINAL CODE: 0009210

AK Designated contracting states

Kind code of ref document: B1

Designated state(s): CH DE FR GB IT LI NL SE

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: CH

Effective date: 19941130

Ref country code: LI

Effective date: 19941130

REF Corresponds to:

Ref document number: 3852220

Country of ref document: DE

Date of ref document: 19950112

ITF It: translation for a ep patent filed

Owner name: STUDIO TORTA SOCIETA' SEMPLICE

ET Fr: translation filed
PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: SE

Effective date: 19950228

REG Reference to a national code

Ref country code: CH

Ref legal event code: PL

PLBE No opposition filed within time limit

Free format text: ORIGINAL CODE: 0009261

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT

26N No opposition filed
PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: NL

Payment date: 19980527

Year of fee payment: 11

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: NL

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20000101

NLV4 Nl: lapsed or anulled due to non-payment of the annual fee

Effective date: 20000101

REG Reference to a national code

Ref country code: GB

Ref legal event code: 732E

REG Reference to a national code

Ref country code: GB

Ref legal event code: IF02

REG Reference to a national code

Ref country code: GB

Ref legal event code: 732E

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: IT

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES;WARNING: LAPSES OF ITALIAN PATENTS WITH EFFECTIVE DATE BEFORE 2007 MAY HAVE OCCURRED AT ANY TIME BEFORE 2007. THE CORRECT EFFECTIVE DATE MAY BE DIFFERENT FROM THE ONE RECORDED.

Effective date: 20050630

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: DE

Payment date: 20070731

Year of fee payment: 20

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: GB

Payment date: 20070628

Year of fee payment: 20

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: FR

Payment date: 20070618

Year of fee payment: 20

REG Reference to a national code

Ref country code: GB

Ref legal event code: PE20

Expiry date: 20080629

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: GB

Free format text: LAPSE BECAUSE OF EXPIRATION OF PROTECTION

Effective date: 20080629